An audio signal processing method includes receiving an audio signal corresponding to a voice of a talker, obtaining an image of the talker, estimating posture information of the talker using the image of the talker, generating a correction filter according to the estimated posture information, performing filter processing on the audio signal using the generated correction filter, and outputting the audio signal on which the filter processing has been performed.
Legal claims defining the scope of protection, as filed with the USPTO.
3. The audio signal processing method according to claim 1, wherein the correction filter is configured to adjust a level of the audio signal.
5. The audio signal processing method according to claim 4, wherein the correction filter is configured to increase a level of the audio signal in a high band or to reduce a level of the audio signal in a low band, as the face of the talker faces farther in the right direction or farther in the left direction.
7. The audio signal processing method according to claim 1, wherein the estimated posture information includes information on a backward-looking posture.
11. The audio signal processing apparatus according to claim 9, wherein the correction filter is configured to adjust a level of the audio signal.
13. The audio signal processing apparatus according to claim 12, wherein the correction filter is configured to increase a level of the audio signal in a high band or to reduce a level of the audio signal in a low band, as the face of the talker faces farther in the right direction or farther in the left direction.
15. The audio signal processing apparatus according to claim 9, wherein the estimated posture information includes information on a backward-looking posture.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
October 4, 2021
April 9, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.